Difference between revisions of "User:Francis Tyers/An MT system in one thousand steps"
Jump to navigation
Jump to search
Line 1: | Line 1: | ||
{{TOCD}} |
{{TOCD}} |
||
+ | |||
+ | ==Research== |
||
+ | |||
+ | * Find a grammar of language X and of language Y |
||
+ | * Find a bilingual dictionary X-Y |
||
+ | * Find bilingual dictionaries X-Z and Y-Z |
||
+ | |||
==Morphological analysers== |
==Morphological analysers== |
||
Line 37: | Line 44: | ||
* Write a contrastive grammar |
* Write a contrastive grammar |
||
+ | |||
+ | ==Evaluation== |
Revision as of 13:21, 30 October 2013
Research
- Find a grammar of language X and of language Y
- Find a bilingual dictionary X-Y
- Find bilingual dictionaries X-Z and Y-Z
Morphological analysers
- Add closed categories
- Add adpositions (1 task)
- Add conjunctions (1 task)
- Add determiners (1 task)
- Add pronouns (1 task)
- Add numerals (1 task)
- At least 1-100 leaving out compositional numerals
- Add open categories
- Add nouns
- Add proper nouns
- Add adjectives
- Add adverbs
- Add verbs
Bilingual dictionary
- Morphologically analyse and word align parallel corpus
- Extract bilingual dictionary candidates
- Proofread and add candidates by frequency
- Find freely available dictionaries online
- Convert to lttoolbox format
Lexical selection
- POS tag and word align parallel corpus
- Extract default translation rules
Disambiguation
- Make a list of most frequent ambiguities
Transfer rules
- Write a contrastive grammar